segmentation loss.py

import tensorflow as tf
from keras.losses import binary_crossentropy
import keras.backend as K

def dice_loss(y_true, y_pred):
    numerator = 2 * tf.reduce_sum(y_true * y_pred, axis=(1,2,3))
    denominator = tf.reduce_sum(y_true + y_pred, axis=(1,2,3))

    return 1 - numerator / denominator

def focal_loss(alpha=0.25, gamma=2):
    def focal_loss_with_logits(logits, targets, alpha, gamma, y_pred):
        weight_a = alpha * (1 - y_pred) ** gamma * targets
        weight_b = (1 - alpha) * y_pred ** gamma * (1 - targets)
        return (tf.log1p(tf.exp(-tf.abs(logits))) + tf.nn.relu(-logits)) * (weight_a + weight_b) + logits * weight_b 

    def loss(y_true, y_pred):
        y_pred = tf.clip_by_value(y_pred, tf.keras.backend.epsilon(), 1 - tf.keras.backend.epsilon())
        logits = tf.log(y_pred / (1 - y_pred))

        loss = focal_loss_with_logits(logits=logits, targets=y_true, alpha=alpha, gamma=gamma, y_pred=y_pred)
        # or reduce_sum and/or axis=-1
        return tf.reduce_mean(loss)
    return loss

def CrossDice_loss(y_true, y_pred):
    def dice_loss(y_true, y_pred):
        numerator = 2 * tf.reduce_sum(y_true * y_pred, axis=(1,2,3))
        denominator = tf.reduce_sum(y_true + y_pred, axis=(1,2,3))

        return tf.reshape(1 - numerator / denominator, (-1, 1, 1))

    return binary_crossentropy(y_true, y_pred) + dice_loss(y_true, y_pred)

def tversky_loss(beta=0.8):
  def loss(y_true, y_pred):
    numerator = tf.reduce_sum(y_true * y_pred, axis=-1)
    denominator = y_true * y_pred + beta * (1 - y_true) * y_pred + (1 - beta) * y_true * (1 - y_pred)

    return 1 - (numerator + 1) / (tf.reduce_sum(denominator, axis=-1) + 1)

  return loss

def focal_tversky(y_true,y_pred):
    pt_1 = tversky_loss()
    gamma = 0.75
    return K.pow((1-pt_1), gamma)